Information processing apparatus, non-transitory computer readable medium, and character recognition system

Abstract

An information processing apparatus includes a processor configured to acquire a result of character recognition of a character string formed on a medium and read by scanning that is subject to character recognition and replace a character or a symbol in a subject with a reference character string that is referred to by the character or the symbol.

What is claimed is: 
     
       1. An information processing apparatus comprising:
 a processor configured to 
 acquire a result of optical character recognition of a character string formed on a medium and read by scanning that is subject to character recognition; 
 determine whether the result of optical character recognition of the character string is a predetermined character or a predetermined symbol that refers to a reference character string that has appeared in a subject previously; 
 search for the reference character string referred to the predetermined character or the predetermined symbol in the subject; and 
 replace the predetermined character or the predetermined symbol in the subject with the reference character string. 
 
     
     
       2. The information processing apparatus according to  claim 1 ,
 wherein the processor is configured to display a verification screen that prompts a user to verify a new character string obtained by the replacing. 
 
     
     
       3. The information processing apparatus according to  claim 2 ,
 wherein the processor is configured to display, as the verification screen, handwritten character strings and the reference character string resulting from the character recognition parallel to each other, the handwritten character strings respectively corresponding to the character or the symbol and the reference character string. 
 
     
     
       4. The information processing apparatus according to  claim 2 ,
 wherein the processor is configured to further display an image of a document having a handwritten character string in addition to the verification screen, and 
 wherein the processor is configured to indicate, in the image of the document, respective positions of a part corresponding to the character or the symbol and a part corresponding to the reference character string. 
 
     
     
       5. The info illation processing apparatus according to  claim 4 ,
 wherein the processor is configured to indicate, in the image of the document, the positions of the part corresponding to the character or the symbol and the part corresponding to the reference character string, the positions being indicated in response to selecting an item in the verification screen by a user. 
 
     
     
       6. The information processing apparatus according to  claim 1 ,
 wherein the processor is configured to search for a character string lying in a direction decided in accordance with the character or the symbol. 
 
     
     
       7. The information processing apparatus according to  claim 6 ,
 wherein the processor is configured to determine the direction on a basis of a position of a frame including a character string. 
 
     
     
       8. The information processing apparatus according to  claim 6 ,
 wherein the processor is configured to compare information regarding a frame including the character or the symbol with information regarding a frame lying in the direction and to set a found character string as a candidate for the reference character string when attributes of content of the frames are identical. 
 
     
     
       9. The information processing apparatus according to  claim 8 ,
 wherein the processor is configured to consider the attributes of the content to be identical when dictionaries used in the character recognition are identical as the attributes. 
 
     
     
       10. The information processing apparatus according to  claim 8 ,
 wherein the processor is configured to select a candidate located closest to the character or the symbol among a plurality of the candidates. 
 
     
     
       11. The information processing apparatus according to  claim 1 ,
 wherein the processor is further configured to 
 replace with the reference character string in a frame immediately above the character or the symbol. 
 
     
     
       12. A non-transitory computer readable medium storing a program causing a computer to execute a process for information management, the process comprising:
 acquiring a result of optical character recognition of a character string formed on a medium and read by scanning that is subject to character recognition; 
 determining whether the result of optical character recognition of the character string is a predetermined character or a predetermined symbol that refers to a reference character string that has appeared in a subject previously; 
 searching for the reference character string referred to the predetermined character or the predetermined symbol in the subject; and 
 replacing the predetermined character or the predetermined symbol in the subject with the reference character string. 
 
     
     
       13. A character recognition system comprising:
 a reader that reads an image of a document having a handwritten character string; 
 a character recognizer that performs character recognition of the handwritten character string; 
 a display that displays a verification screen that prompts a user to verify a result of the character recognition by the character recognizer; and 
 an image generator that generates an image of the verification screen, 
 the image generator including a processor configured to 
 acquire the result of the character recognition from the character recognizer and 
 in response to a determination that the handwritten character string includes a character or a symbol that refers to a reference character string that has appeared previously, replace the character or the symbol with the reference character string that is referred to by the character or the symbol.